Conditional Neural Architecture Search
This work addresses the challenge of deploying ML models on edge platforms with varying performance, power, and memory constraints, though it appears incremental by combining existing techniques in a new way.
The paper tackles the problem of designing resource-efficient deep neural networks for diverse edge platforms by proposing a conditional neural architecture search method using GANs, which successfully generates constraint-optimized MLP or CNN-based networks for regression and classification on CIFAR-10.
Designing resource-efficient Deep Neural Networks (DNNs) is critical to deploy deep learning solutions over edge platforms due to diverse performance, power, and memory budgets. Unfortunately, it is often the case a well-trained ML model does not fit to the constraint of deploying edge platforms, causing a long iteration of model reduction and retraining process. Moreover, a ML model optimized for platform-A often may not be suitable when we deploy it on another platform-B, causing another iteration of model retraining. We propose a conditional neural architecture search method using GAN, which produces feasible ML models for different platforms. We present a new workflow to generate constraint-optimized DNN models. This is the first work of bringing in condition and adversarial technique into Neural Architecture Search domain. We verify the method with regression problems and classification on CIFAR-10. The proposed workflow can successfully generate resource-optimized MLP or CNN-based networks.